codex-review
Warn
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct users to download and install content from a GitHub repository (BenedictKing/codex-review) that is not associated with a recognized trusted organization or the registered author (sickn33).\n- [REMOTE_CODE_EXECUTION]: The installation command
npx skills addretrieves and executes remote code from an unverified third-party source into the local environment.\n- [PROMPT_INJECTION]: The skill processes external source code for review, which introduces a surface for indirect prompt injection if the ingested data contains malicious instructions.\n - Ingestion points: The skill ingests user source code for review and changelog generation.\n
- Boundary markers: The instructions do not specify the use of delimiters or isolation protocols to prevent the agent from obeying instructions embedded within the reviewed code.\n
- Capability inventory: The skill performs code analysis and possesses the capability to write to the file system (generating CHANGELOG.md).\n
- Sanitization: There is no evidence of sanitization or validation of the input code before it is processed by the AI agent.
Audit Metadata